Using Bayesian networks for the assessment of underwater scour for road and railway bridges

Andrea Maroni, Enrico Tubaldi, John Douglas, Neil Ferguson, Daniele Zonta, Hazel McDonald, Douglas Walker, Euan Greenoak, Christopher Green

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Flood-induced scour is by far the leading cause of bridge failures, resulting in loss of lives, traffic disruption and significant economic losses. In Scotland, there are around 2,000 structures, considering both road and railway bridges, susceptible to scour. Scour assessments are currently based on visual inspections, which are expensive, time-consuming, and often the information collected is qualitative and subjective. The two main transport agencies in Scotland, Transport Scotland and Network Rail, spend £2m and £0.4m per annum, respectively, in routine inspections. Nowadays sensor and communication technologies offer the possibility to assess in real time the scour depth at critical bridge locations; yet monitoring an entire infrastructure network is not economically sustainable. A way to overcome this limitation is to install monitoring systems on a limited number of critical locations and use a probabilistic approach to extend this information to the entire population of assets. The state of the bridge stock is represented through a set of random variables and ad-hoc Bayesian networks (BNs) are used to describe their conditional dependencies. The aim of this paper is to develop a probabilistic scour hazard model by building a BN able to estimate the depth of scour in the surrounding of bridge foundations. The BN can estimate, and continuously update, the present and future scour depth using real-time information from monitoring of scour depth and river flow characteristics. In the occurrence of a flood, monitoring observations are used to infer the posterior distribution of the state variables probabilistically, and therefore to give in real-time the best estimate of total scour depth. Bias, systematic and model uncertainties are modelled as nodes of the BN in such a way as the accuracy of predictions can be updated when information from the scour monitoring system is incorporated into the BN. In order to demonstrate the functioning of the BN, bridges managed by TS in South-West Scotland were used to build a small bridge network. They cross the same river (River Nith) and only one of them is instrumented with a scour monitoring system.
LanguageEnglish
Title of host publicationStructural Faults and Repair and European Bridge Conference 2018
Subtitle of host publicationConference Proceedings
Place of PublicationBirmingham, UK
Number of pages13
StatePublished - 17 May 2018
Event17th European Bridge Conference 2018 - Radisson Blue Hotel, Royal Mile, Edinburgh , United Kingdom
Duration: 15 May 201817 May 2018
http://www.structuralfaultsandrepair.com

Conference

Conference17th European Bridge Conference 2018
Abbreviated titleEuro-Bridge-2018
CountryUnited Kingdom
CityEdinburgh
Period15/05/1817/05/18
Internet address

Fingerprint

Scour
Bayesian networks
Monitoring
Rivers
Inspection
Random variables
Rails
Hazards

Keywords

  • scour
  • road and rail bridges
  • structural health monitoring
  • Bayesian network

Cite this

Maroni, A., Tubaldi, E., Douglas, J., Ferguson, N., Zonta, D., McDonald, H., ... Green, C. (2018). Using Bayesian networks for the assessment of underwater scour for road and railway bridges. In Structural Faults and Repair and European Bridge Conference 2018: Conference Proceedings Birmingham, UK.
Maroni, Andrea ; Tubaldi, Enrico ; Douglas, John ; Ferguson, Neil ; Zonta, Daniele ; McDonald, Hazel ; Walker, Douglas ; Greenoak, Euan ; Green, Christopher. / Using Bayesian networks for the assessment of underwater scour for road and railway bridges. Structural Faults and Repair and European Bridge Conference 2018: Conference Proceedings. Birmingham, UK, 2018.
@inproceedings{09f1a26f730342d98d13b0cd45b7556e,
title = "Using Bayesian networks for the assessment of underwater scour for road and railway bridges",
abstract = "Flood-induced scour is by far the leading cause of bridge failures, resulting in loss of lives, traffic disruption and significant economic losses. In Scotland, there are around 2,000 structures, considering both road and railway bridges, susceptible to scour. Scour assessments are currently based on visual inspections, which are expensive, time-consuming, and often the information collected is qualitative and subjective. The two main transport agencies in Scotland, Transport Scotland and Network Rail, spend £2m and £0.4m per annum, respectively, in routine inspections. Nowadays sensor and communication technologies offer the possibility to assess in real time the scour depth at critical bridge locations; yet monitoring an entire infrastructure network is not economically sustainable. A way to overcome this limitation is to install monitoring systems on a limited number of critical locations and use a probabilistic approach to extend this information to the entire population of assets. The state of the bridge stock is represented through a set of random variables and ad-hoc Bayesian networks (BNs) are used to describe their conditional dependencies. The aim of this paper is to develop a probabilistic scour hazard model by building a BN able to estimate the depth of scour in the surrounding of bridge foundations. The BN can estimate, and continuously update, the present and future scour depth using real-time information from monitoring of scour depth and river flow characteristics. In the occurrence of a flood, monitoring observations are used to infer the posterior distribution of the state variables probabilistically, and therefore to give in real-time the best estimate of total scour depth. Bias, systematic and model uncertainties are modelled as nodes of the BN in such a way as the accuracy of predictions can be updated when information from the scour monitoring system is incorporated into the BN. In order to demonstrate the functioning of the BN, bridges managed by TS in South-West Scotland were used to build a small bridge network. They cross the same river (River Nith) and only one of them is instrumented with a scour monitoring system.",
keywords = "scour, road and rail bridges, structural health monitoring, Bayesian network",
author = "Andrea Maroni and Enrico Tubaldi and John Douglas and Neil Ferguson and Daniele Zonta and Hazel McDonald and Douglas Walker and Euan Greenoak and Christopher Green",
year = "2018",
month = "5",
day = "17",
language = "English",
booktitle = "Structural Faults and Repair and European Bridge Conference 2018",

}

Maroni, A, Tubaldi, E, Douglas, J, Ferguson, N, Zonta, D, McDonald, H, Walker, D, Greenoak, E & Green, C 2018, Using Bayesian networks for the assessment of underwater scour for road and railway bridges. in Structural Faults and Repair and European Bridge Conference 2018: Conference Proceedings. Birmingham, UK, 17th European Bridge Conference 2018, Edinburgh , United Kingdom, 15/05/18.

Using Bayesian networks for the assessment of underwater scour for road and railway bridges. / Maroni, Andrea; Tubaldi, Enrico; Douglas, John; Ferguson, Neil; Zonta, Daniele; McDonald, Hazel; Walker, Douglas; Greenoak, Euan; Green, Christopher.

Structural Faults and Repair and European Bridge Conference 2018: Conference Proceedings. Birmingham, UK, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Using Bayesian networks for the assessment of underwater scour for road and railway bridges

AU - Maroni,Andrea

AU - Tubaldi,Enrico

AU - Douglas,John

AU - Ferguson,Neil

AU - Zonta,Daniele

AU - McDonald,Hazel

AU - Walker,Douglas

AU - Greenoak,Euan

AU - Green,Christopher

PY - 2018/5/17

Y1 - 2018/5/17

N2 - Flood-induced scour is by far the leading cause of bridge failures, resulting in loss of lives, traffic disruption and significant economic losses. In Scotland, there are around 2,000 structures, considering both road and railway bridges, susceptible to scour. Scour assessments are currently based on visual inspections, which are expensive, time-consuming, and often the information collected is qualitative and subjective. The two main transport agencies in Scotland, Transport Scotland and Network Rail, spend £2m and £0.4m per annum, respectively, in routine inspections. Nowadays sensor and communication technologies offer the possibility to assess in real time the scour depth at critical bridge locations; yet monitoring an entire infrastructure network is not economically sustainable. A way to overcome this limitation is to install monitoring systems on a limited number of critical locations and use a probabilistic approach to extend this information to the entire population of assets. The state of the bridge stock is represented through a set of random variables and ad-hoc Bayesian networks (BNs) are used to describe their conditional dependencies. The aim of this paper is to develop a probabilistic scour hazard model by building a BN able to estimate the depth of scour in the surrounding of bridge foundations. The BN can estimate, and continuously update, the present and future scour depth using real-time information from monitoring of scour depth and river flow characteristics. In the occurrence of a flood, monitoring observations are used to infer the posterior distribution of the state variables probabilistically, and therefore to give in real-time the best estimate of total scour depth. Bias, systematic and model uncertainties are modelled as nodes of the BN in such a way as the accuracy of predictions can be updated when information from the scour monitoring system is incorporated into the BN. In order to demonstrate the functioning of the BN, bridges managed by TS in South-West Scotland were used to build a small bridge network. They cross the same river (River Nith) and only one of them is instrumented with a scour monitoring system.

AB - Flood-induced scour is by far the leading cause of bridge failures, resulting in loss of lives, traffic disruption and significant economic losses. In Scotland, there are around 2,000 structures, considering both road and railway bridges, susceptible to scour. Scour assessments are currently based on visual inspections, which are expensive, time-consuming, and often the information collected is qualitative and subjective. The two main transport agencies in Scotland, Transport Scotland and Network Rail, spend £2m and £0.4m per annum, respectively, in routine inspections. Nowadays sensor and communication technologies offer the possibility to assess in real time the scour depth at critical bridge locations; yet monitoring an entire infrastructure network is not economically sustainable. A way to overcome this limitation is to install monitoring systems on a limited number of critical locations and use a probabilistic approach to extend this information to the entire population of assets. The state of the bridge stock is represented through a set of random variables and ad-hoc Bayesian networks (BNs) are used to describe their conditional dependencies. The aim of this paper is to develop a probabilistic scour hazard model by building a BN able to estimate the depth of scour in the surrounding of bridge foundations. The BN can estimate, and continuously update, the present and future scour depth using real-time information from monitoring of scour depth and river flow characteristics. In the occurrence of a flood, monitoring observations are used to infer the posterior distribution of the state variables probabilistically, and therefore to give in real-time the best estimate of total scour depth. Bias, systematic and model uncertainties are modelled as nodes of the BN in such a way as the accuracy of predictions can be updated when information from the scour monitoring system is incorporated into the BN. In order to demonstrate the functioning of the BN, bridges managed by TS in South-West Scotland were used to build a small bridge network. They cross the same river (River Nith) and only one of them is instrumented with a scour monitoring system.

KW - scour

KW - road and rail bridges

KW - structural health monitoring

KW - Bayesian network

UR - http://www.structuralfaultsandrepair.com/

M3 - Conference contribution

BT - Structural Faults and Repair and European Bridge Conference 2018

CY - Birmingham, UK

ER -

Maroni A, Tubaldi E, Douglas J, Ferguson N, Zonta D, McDonald H et al. Using Bayesian networks for the assessment of underwater scour for road and railway bridges. In Structural Faults and Repair and European Bridge Conference 2018: Conference Proceedings. Birmingham, UK. 2018.